| Name | jquants-ml JSON |
| Version |
0.1.4
JSON |
| download |
| home_page | |
| Summary | jquants-ml is a python library for machine learning with japanese stock trade using J-Quants on Python 3.8 and above. |
| upload_time | 2023-10-24 13:19:31 |
| maintainer | |
| docs_url | None |
| author | |
| requires_python | >=3.8 |
| license | |
| keywords |
machine learning
python
japanese stock
trade
j-quants
jquants
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# jquants-ml
[](https://pypi.org/project/jquants-ml/)
[](https://opensource.org/licenses/MIT)
[](https://codecov.io/gh/10mohi6/jquants-ml-python)
[](https://github.com/10mohi6/jquants-ml-python/actions/workflows/python-package.yml)
[](https://pypi.org/project/jquants-ml/)
[](https://pepy.tech/project/jquants-ml)
jquants-ml is a python library for machine learning with japanese stock trade using J-Quants on Python 3.8 and above.
## Installation
$ pip install jquants-ml
## Usage
### backtest
```python
from jquants_ml import Ml
import pprint
class MyMl(Ml):
def features(self):
self.X["close"] = self.df.Close
self.X["ror"] = self.df.Close.pct_change(1)
self.X["sma"] = self.sma(period=5)
ml = MyMl(
mail_address="<your J-Quants mail address>",
password="<your J-Quants password>",
ticker="7203", # TOYOTA
size=100, # 100 shares
)
pprint.pprint(ml.backtest())
```
```python
{'long': {'maximum drawdown': '15250.000',
'profit': '12700.000',
'profit factor': '1.183',
'riskreward ratio': '1.213',
'sharpe ratio': '0.063',
'trades': '81.000',
'win rate': '0.494'},
'short': {'maximum drawdown': '50100.000',
'profit': '-43800.000',
'profit factor': '0.413',
'riskreward ratio': '0.478',
'sharpe ratio': '0.298',
'trades': '41.000',
'win rate': '0.463'},
'total': {'maximum drawdown': '47200.000',
'profit': '-31100.000',
'profit factor': '0.784',
'riskreward ratio': '0.837',
'sharpe ratio': '0.149',
'trades': '122.000',
'win rate': '0.484'}}
```
### predict
```python
from jquants_ml import Ml
import pprint
class MyMl(Ml):
def features(self):
self.X["close"] = self.df.Close
self.X["ror"] = self.df.Close.pct_change(1)
self.X["sma"] = self.sma(period=5)
ml = MyMl(
mail_address="<your J-Quants mail address>",
password="<your J-Quants password>",
ticker="7203", # TOYOTA
size=100, # 100 shares
)
pprint.pprint(ml.predict())
```
```python
{'Date': '2023-08-01', 'Price': 2445.5, 'Sign': 'short'}
```
### advanced
```python
from jquants_ml import Ml
class MyMl(Ml):
# Awesome Oscillator
def ao(self, *, fast_period: int = 5, slow_period: int = 34):
return ((self.df.H + self.df.L) / 2).rolling(fast_period).mean() - (
(self.df.H + self.df.L) / 2
).rolling(slow_period).mean()
def features(self):
self.X["ao"] = self.ao(fast_period=5, slow_period=34)
self.X["close"] = self.df.Close
self.X["ror"] = self.df.Close.pct_change(1)
self.X["sma"] = self.sma(period=5)
self.X["ema"] = self.ema(period=5)
self.X["upper"], self.X["mid"], self.X["lower"] = self.bbands(
period=20, band=2
)
self.X["macd"], self.X["signal"] = self.macd(
fast_period=12, slow_period=26, signal_period=9
)
self.X["k"], self.X["d"] = self.stoch(k_period=5, d_period=3)
self.X["rsi"] = self.rsi(period=14)
self.X["atr"] = self.atr(period=14)
self.X["mom"] = self.mom(period=10)
ml = MyMl(
mail_address="<your J-Quants mail address>",
password="<your J-Quants password>",
ticker="7203", # TOYOTA
size=100, # 100 shares
outputs_dir_path="outputs",
model_dir_path="model",
data_dir_path="data",
)
pprint.pprint(ml.backtest())
pprint.pprint(ml.predict())
```
## Supported indicators
- Simple Moving Average 'sma'
- Exponential Moving Average 'ema'
- Moving Average Convergence Divergence 'macd'
- Relative Strenght Index 'rsi'
- Bollinger Bands 'bbands'
- Market Momentum 'mom'
- Stochastic Oscillator 'stoch'
- Average True Range 'atr'
## Getting started
For help getting started with J-Quants, view our online [documentation](https://jpx-jquants.com/).
Raw data
{
"_id": null,
"home_page": "",
"name": "jquants-ml",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "",
"keywords": "machine learning,python,japanese stock,trade,J-Quants,jquants",
"author": "",
"author_email": "10mohi6 <10.mohi.6.y@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/29/7f/4d765a6bb8fc8c3269832ae87d7c4ef95146958afcba5277f2b89dcbdea9/jquants-ml-0.1.4.tar.gz",
"platform": null,
"description": "# jquants-ml\n\n[](https://pypi.org/project/jquants-ml/)\n[](https://opensource.org/licenses/MIT)\n[](https://codecov.io/gh/10mohi6/jquants-ml-python)\n[](https://github.com/10mohi6/jquants-ml-python/actions/workflows/python-package.yml)\n[](https://pypi.org/project/jquants-ml/)\n[](https://pepy.tech/project/jquants-ml)\n\njquants-ml is a python library for machine learning with japanese stock trade using J-Quants on Python 3.8 and above.\n\n## Installation\n\n $ pip install jquants-ml\n\n## Usage\n\n### backtest\n\n```python\nfrom jquants_ml import Ml\nimport pprint\n\nclass MyMl(Ml):\n def features(self):\n self.X[\"close\"] = self.df.Close\n self.X[\"ror\"] = self.df.Close.pct_change(1)\n self.X[\"sma\"] = self.sma(period=5)\n\nml = MyMl(\n mail_address=\"<your J-Quants mail address>\",\n password=\"<your J-Quants password>\",\n ticker=\"7203\", # TOYOTA\n size=100, # 100 shares\n)\npprint.pprint(ml.backtest())\n```\n\n\n\n```python\n{'long': {'maximum drawdown': '15250.000',\n 'profit': '12700.000',\n 'profit factor': '1.183',\n 'riskreward ratio': '1.213',\n 'sharpe ratio': '0.063',\n 'trades': '81.000',\n 'win rate': '0.494'},\n 'short': {'maximum drawdown': '50100.000',\n 'profit': '-43800.000',\n 'profit factor': '0.413',\n 'riskreward ratio': '0.478',\n 'sharpe ratio': '0.298',\n 'trades': '41.000',\n 'win rate': '0.463'},\n 'total': {'maximum drawdown': '47200.000',\n 'profit': '-31100.000',\n 'profit factor': '0.784',\n 'riskreward ratio': '0.837',\n 'sharpe ratio': '0.149',\n 'trades': '122.000',\n 'win rate': '0.484'}}\n```\n\n### predict\n\n```python\nfrom jquants_ml import Ml\nimport pprint\n\nclass MyMl(Ml):\n def features(self):\n self.X[\"close\"] = self.df.Close\n self.X[\"ror\"] = self.df.Close.pct_change(1)\n self.X[\"sma\"] = self.sma(period=5)\n\nml = MyMl(\n mail_address=\"<your J-Quants mail address>\",\n password=\"<your J-Quants password>\",\n ticker=\"7203\", # TOYOTA\n size=100, # 100 shares\n)\npprint.pprint(ml.predict())\n```\n\n```python\n{'Date': '2023-08-01', 'Price': 2445.5, 'Sign': 'short'}\n```\n\n### advanced\n\n```python\nfrom jquants_ml import Ml\n\nclass MyMl(Ml):\n # Awesome Oscillator\n def ao(self, *, fast_period: int = 5, slow_period: int = 34):\n return ((self.df.H + self.df.L) / 2).rolling(fast_period).mean() - (\n (self.df.H + self.df.L) / 2\n ).rolling(slow_period).mean()\n\n def features(self):\n self.X[\"ao\"] = self.ao(fast_period=5, slow_period=34)\n self.X[\"close\"] = self.df.Close\n self.X[\"ror\"] = self.df.Close.pct_change(1)\n self.X[\"sma\"] = self.sma(period=5)\n self.X[\"ema\"] = self.ema(period=5)\n self.X[\"upper\"], self.X[\"mid\"], self.X[\"lower\"] = self.bbands(\n period=20, band=2\n )\n self.X[\"macd\"], self.X[\"signal\"] = self.macd(\n fast_period=12, slow_period=26, signal_period=9\n )\n self.X[\"k\"], self.X[\"d\"] = self.stoch(k_period=5, d_period=3)\n self.X[\"rsi\"] = self.rsi(period=14)\n self.X[\"atr\"] = self.atr(period=14)\n self.X[\"mom\"] = self.mom(period=10)\n\nml = MyMl(\n mail_address=\"<your J-Quants mail address>\",\n password=\"<your J-Quants password>\",\n ticker=\"7203\", # TOYOTA\n size=100, # 100 shares\n outputs_dir_path=\"outputs\",\n model_dir_path=\"model\",\n data_dir_path=\"data\",\n)\npprint.pprint(ml.backtest())\npprint.pprint(ml.predict())\n```\n\n## Supported indicators\n\n- Simple Moving Average 'sma'\n- Exponential Moving Average 'ema'\n- Moving Average Convergence Divergence 'macd'\n- Relative Strenght Index 'rsi'\n- Bollinger Bands 'bbands'\n- Market Momentum 'mom'\n- Stochastic Oscillator 'stoch'\n- Average True Range 'atr'\n\n## Getting started\n\nFor help getting started with J-Quants, view our online [documentation](https://jpx-jquants.com/).\n",
"bugtrack_url": null,
"license": "",
"summary": "jquants-ml is a python library for machine learning with japanese stock trade using J-Quants on Python 3.8 and above.",
"version": "0.1.4",
"project_urls": {
"Documentation": "https://github.com/10mohi6/jquants-ml-python",
"Homepage": "https://github.com/10mohi6/jquants-ml-python",
"Repository": "https://github.com/10mohi6/jquants-ml-python.git"
},
"split_keywords": [
"machine learning",
"python",
"japanese stock",
"trade",
"j-quants",
"jquants"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "ef603f6afcdbca90b8bf491d700523929fb89684e8dd430eb3372cd9df253278",
"md5": "572a060ccd2c328e296a8a3fdcf322c4",
"sha256": "55eb24e0891ac5d26cda397bf30a34281ab47c400e249741de10a868ffc7e1b3"
},
"downloads": -1,
"filename": "jquants_ml-0.1.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "572a060ccd2c328e296a8a3fdcf322c4",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 6765,
"upload_time": "2023-10-24T13:19:27",
"upload_time_iso_8601": "2023-10-24T13:19:27.272889Z",
"url": "https://files.pythonhosted.org/packages/ef/60/3f6afcdbca90b8bf491d700523929fb89684e8dd430eb3372cd9df253278/jquants_ml-0.1.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "297f4d765a6bb8fc8c3269832ae87d7c4ef95146958afcba5277f2b89dcbdea9",
"md5": "faa5f7692f086a1b917af027135fc00c",
"sha256": "83241eb992dcf1c80cd1f684b8592ce6409eea0cf6588eecb002d62534081df5"
},
"downloads": -1,
"filename": "jquants-ml-0.1.4.tar.gz",
"has_sig": false,
"md5_digest": "faa5f7692f086a1b917af027135fc00c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 7387,
"upload_time": "2023-10-24T13:19:31",
"upload_time_iso_8601": "2023-10-24T13:19:31.176226Z",
"url": "https://files.pythonhosted.org/packages/29/7f/4d765a6bb8fc8c3269832ae87d7c4ef95146958afcba5277f2b89dcbdea9/jquants-ml-0.1.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-10-24 13:19:31",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "10mohi6",
"github_project": "jquants-ml-python",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "jquants-ml"
}
